Identification of Pan-Cancer Biomarkers Based on the Gene Expression Profiles of Cancer Cell Lines

Abstract

There are many types of cancers. Although they share some hallmarks, such as proliferation and metastasis, they are still very different from many perspectives. They grow on different organ or tissues. Does each cancer have a unique gene expression pattern that makes it different from other cancer types? After the Cancer Genome Atlas (TCGA) project, there are more and more pan-cancer studies. Researchers want to get robust gene expression signature from pan-cancer patients. But there is large variance in cancer patients due to heterogeneity. To get robust results, the sample size will be too large to recruit. In this study, we tried another approach to get robust pan-cancer biomarkers by using the cell line data to reduce the variance. We applied several advanced computational methods to analyze the Cancer Cell Line Encyclopedia (CCLE) gene expression profiles which included 988 cell lines from 20 cancer types. Two feature selection methods, including Boruta, and max-relevance and min-redundancy methods, were applied to the cell line gene expression data one by one, generating a feature list. Such list was fed into incremental feature selection method, incorporating one classification algorithm, to extract biomarkers, construct optimal classifiers and decision rules. The optimal classifiers provided good performance, which can be useful tools to identify cell lines from different cancer types, whereas the biomarkers (e.g. NCKAP1, TNFRSF12A, LAMB2, FKBP9, PFN2, TOM1L1) and rules identified in this work may provide a meaningful and precise reference for differentiating multiple types of cancer and contribute to the personalized treatment of tumors.

Computed Tomography Imaging-Based Radiogenomics Analysis Reveals Hypoxia Patterns and Immunological Characteristics in Ovarian Cancer

“…In lung cancer, key genes for disease progression were identified by various bioinformatics methods ( 9 ). Interestingly, cancer cell lines can also be identified by the incremental feature selection method ( 10 ). For OC, the ceRNA network was constructed, and novel insights of the regulatory mechanisms among mRNAs, lncRNAs, and miRNAs were provided ( 11 ).…”

Identifying COVID-19 Severity-Related SARS-CoV-2 Mutation Using a Machine Learning Method

“…A large number of redundant features exist among all mutation features, and they are not very helpful in distinguishing patients’ clinical status and can become noisy features for subsequent modeling. Boruta can filter the set of all features that have a correlation with the dependent variable, and the experimental results are very stable and scalable [ 20 , 21 ]. Here, we used Boruta for the initial filtering of mutation features, which is implemented as described below.…”

Identification of protein–protein interaction associated functions based on gene ontology and KEGG pathway

“…Boruta, a wrapper-based feature selection method, uses random forest as the classifier to filter out a set of features that are relevant to the target variable ( Kursa and Rudnicki, 2010 ; Zhang et al, 2020 ; Chen et al, 2021 ; Ding et al, 2021 ; Zhou et al, 2022 ). It is implemented through the following steps: 1) The features are randomly shuffled and then stitch together with the actual feature matrix to form a new feature matrix.…”